Hedonometer

Last updated

A hedonometer or hedonimeter is a device used to gauge happiness or pleasure. Conceived of at least as early as 1880, [1] the term was used in 1881 by the economist Francis Ysidro Edgeworth to describe "an ideally perfect instrument, a psychophysical machine, continually registering the height of pleasure experienced by an individual." [2]

Contents

More recently, it has been used to refer to a tool developed by Peter Dodds and Chris Danforth to gauge the valence of various corpora, including historical State of the Union addresses, song lyrics, and online tweets and blogs. [3] [4] [5] It is operated out of the University of Vermont (UVM), and has been in use since 2008. [6] A version of the tool is available at hedonometer.org, which they call a sort of "Dow Jones Index of Happiness", [7] and hope will be used by government officials in conjunction with other metrics as a gauge of the population's well-being. [8]

Computer scientists trained the hedonometer to recognize the emotion behind data as tweets with sentiment analysis techniques. Danforth preferred a lexicon approach, that measures the weight of a word, due to the energy required for neural nets. [9]

As of 2020, the hedonometer at UVM scrapes about 50 million tweets each day. Using sentiment analysis, the hedonometer takes the emotional temperature of the words published by users of various platforms. [6]

See also

Related Research Articles

In ethical philosophy, utilitarianism is a family of normative ethical theories that prescribe actions that maximize happiness and well-being for the affected individuals. In other words, utilitarian ideas encourage actions that ensure the greatest good for the greatest number. Although different varieties of utilitarianism admit different characterizations, the basic idea behind all of them is, in some sense, to maximize utility, which is often defined in terms of well-being or related concepts. For instance, Jeremy Bentham, the founder of utilitarianism, described utility thus:

That property in any object, whereby it tends to produce benefit, advantage, pleasure, good, or happiness ... [or] to prevent the happening of mischief, pain, evil, or unhappiness to the party whose interest is considered.

<span class="mw-page-title-main">Happiness</span> Mental state, noted for pleasant emotions

Happiness is a positive and pleasant emotion, ranging from contentment to intense joy. Moments of happiness may be triggered by positive life experiences or thoughts, but sometimes it may arise from no obvious cause. The level of happiness for longer periods of time is more strongly correlated with levels of life satisfaction, subjective well-being, flourishing and eudaimonia. In common usage, the word happy can be an appraisal of those measures themselves or as a shorthand for a "source" of happiness. As with any emotion, the precise definition of happiness has been a perennial debate in philosophy.

Eudaimonia, sometimes anglicized as eudaemonia or eudemonia, is a Greek word literally translating to the state or condition of 'good spirit', and which is commonly translated as 'happiness' or 'welfare'.

<span class="mw-page-title-main">Cardinal utility</span> In contrast with ordinal utility, in economics

In economics, a cardinal utility function or scale is a utility index that preserves preference orderings uniquely up to positive affine transformations. Two utility indices are related by an affine transformation if for the value of one index u, occurring at any quantity of the goods bundle being evaluated, the corresponding value of the other index v satisfies a relationship of the form

Sentiment analysis is the use of natural language processing, text analysis, computational linguistics, and biometrics to systematically identify, extract, quantify, and study affective states and subjective information. Sentiment analysis is widely applied to voice of the customer materials such as reviews and survey responses, online and social media, and healthcare materials for applications that range from marketing to customer service to clinical medicine. With the rise of deep language models, such as RoBERTa, also more difficult data domains can be analyzed, e.g., news texts where authors typically express their opinion/sentiment less explicitly.

The economics of happiness or happiness economics is the theoretical, qualitative and quantitative study of happiness and quality of life, including positive and negative affects, well-being, life satisfaction and related concepts – typically tying economics more closely than usual with other social sciences, like sociology and psychology, as well as physical health. It typically treats subjective happiness-related measures, as well as more objective quality of life indices, rather than wealth, income or profit, as something to be maximized.

The philosophy of happiness is the philosophical concern with the existence, nature, and attainment of happiness. Some philosophers believe happiness can be understood as the moral goal of life or as an aspect of chance; indeed, in most European languages the term happiness is synonymous with luck. Thus, philosophers usually explicate on happiness as either a state of mind, or a life that goes well for the person leading it. Given the pragmatic concern for the attainment of happiness, research in psychology has guided many modern-day philosophers in developing their theories.

Wikiprogress is a defunct online platform for sharing information on the measurement of social, economic and environmental progress. It is thought to facilitate sharing on ideas, initiatives and knowledge on "measuring the progress of societies". Like Wikipedia, it was open to all members and communities for contribution – anyone interested in "progress" could register.

Culturomics is a form of computational lexicology that studies human behavior and cultural trends through the quantitative analysis of digitized texts. Researchers data mine large digital archives to investigate cultural phenomena reflected in language and word usage. The term is an American neologism first described in a 2010 Science article called Quantitative Analysis of Culture Using Millions of Digitized Books, co-authored by Harvard researchers Jean-Baptiste Michel and Erez Lieberman Aiden.

Shadow banning, also called stealth banning, hellbanning, ghost banning, and comment ghosting, is the practice of blocking or partially blocking a user or the user's content from some areas of an online community in such a way that the ban is not readily apparent to the user, regardless of whether the action is taken by an individual or an algorithm. For example, shadow-banned comments posted to a blog or media website would be visible to the sender, but not to other users accessing the site.

Subjective well-being (SWB) is a self-reported measure of well-being, typically obtained by questionnaire.

BackTweets is a Twitter analytics tool which allows users to search through a Tweet archive for links, including shortened URLs that were sent on Twitter.

Robert P. Schumaker is an American academic and Professor of computer science at the University of Texas at Tyler, best known for creating AZFinText, a news-aware high-frequency stock trading system. Schumaker is also known as a Sports Analytics expert for his pioneering work using Twitter tweet sentiment to predict sports outcomes and is currently active in both prescription drug interactions and covid-19 vaccine allergies. Schumaker is also the founder and Director of the Data Analytics Lab.

<span class="mw-page-title-main">Topsy Labs</span> U.S. social search and analytics company

Topsy Labs was a social search and analytics company based in San Francisco, California. The company was a certified Twitter partner and maintained a comprehensive index of tweets, numbering in the hundreds of billions, dating back to Twitter's inception in 2006.

<span class="mw-page-title-main">Bottlenose (company)</span>

Bottlenose.com, also known as Bottlenose, is an enterprise trend intelligence company that analyzes big data and business data to detect trends for brands. It helps Fortune 500 enterprises discover, and track emerging trends that affect their brands. The company uses natural language processing, sentiment analysis, statistical algorithms, data mining, and machine learning heuristics to determine trends, and has a search engine that gathers information from social networks. KPMG Capital has invested a "substantial amount" in the company.

Social media mining is the process of obtaining data from user-generated content on social media in order to extract actionable patterns, form conclusions about users, and act upon the information. Mining supports targeting advertising to users or academic research. The term is an analogy to the process of mining for minerals. Mining companies sift through raw ore to find the valuable minerals; likewise, social media mining sifts through social media data in order to discern patterns and trends about matters such as social media usage, online behaviour, content sharing, connections between individuals, buying behaviour. These patterns and trends are of interest to companies, governments and not-for-profit organizations, as such organizations can use the analyses for tasks such as design strategies, introduce programs, products, processes or services.

Emotion recognition is the process of identifying human emotion. People vary widely in their accuracy at recognizing the emotions of others. Use of technology to help people with emotion recognition is a relatively nascent research area. Generally, the technology works best if it uses multiple modalities in context. To date, the most work has been conducted on automating the recognition of facial expressions from video, spoken expressions from audio, written expressions from text, and physiology as measured by wearables.

Jason Goepfert is an American researcher and columnist focused on the development of behavioral finance. Prior to founding Sundial Capital Research, he was the manager of back office operations for Deephaven Capital Management, a Minnesota-based hedge fund, and Wells Fargo's online brokerage unit.

Chris Danforth is a computer scientist and a professor of applied mathematics at the University of Vermont. He is known for his work with the Hedonometer, a tool developed for measuring collective mood with sentiment analysis.

Peter Sheridan Dodds is an Australian applied Mathematician. He is the director of the Vermont Complex Systems Center and Professor at the University of Vermont's Department of Mathematics and Statistics. He has collaborated in several researches related to big data problems in areas as language, stories, sociotechnical systems, Earth science, biology, and ecology. With Chris Danforth, he co-runs the Computational Story Lab, the MassMutual Center of Excellence in Complex Systems and Data Science, and together, they developed the hedonometer.

References

  1. Oxford English Dictionary definition
  2. Edgeworth's Hedonimeter and the Quest to Measure Utility
  3. Reuters - "Jackson's death was blogosphere's saddest day: study"
  4. Dodds, Peter Sheridan; Danforth, Christopher M. (2010). "Measuring the Happiness of Large-Scale Written Expression: Songs, Blogs, and Presidents". Journal of Happiness Studies. 11 (4): 441–456. doi:10.1007/s10902-009-9150-9.
  5. The Atlantic - "The Geography of Happiness According to 10 Million Tweets"
  6. 1 2 Mackenzie, Dana (2020-09-14). "How algorithms discern our mood from what we write online". Knowable Magazine. doi: 10.1146/knowable-091120-1 . S2CID   242984992.
  7. Computational Story Lab - "Now online: the Dow Jones Index of Happiness"
  8. Bloomberg Businessweek - "Forget GDP. Data Crunchers Measure Happy Tweets for Key Economic Indicator"
  9. Mackenzie, Dana; Magazine, Knowable (19 September 2020). "How Algorithms Discern Our Mood From What We Write Online". The Wire Science.